Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search

Shuo Huang, Xingliang Yuan, Gholamreza Haffari, Lizhen Qu


Abstract
The increasing adoption of large language models (LLMs) in cloud-based services has raised significant privacy concerns, as user inputs may inadvertently expose sensitive information. Existing text anonymization and de-identification techniques, such as rule-based redaction and scrubbing, often struggle to balance privacy preservation with text naturalness and utility. In this work, we propose a zero-shot, tree-search-based iterative sentence rewriting algorithm that systematically obfuscates or deletes private information while preserving coherence, relevance, and naturalness. Our method incrementally rewrites privacy-sensitive segments through a structured search guided by a reward model, enabling dynamic exploration of the rewriting space. Experiments on privacy-sensitive datasets show that our approach significantly outperforms existing baselines, achieving a superior balance between privacy protection and utility preservation.
Anthology ID:
2025.findings-emnlp.488
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9175–9190
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.488/
DOI:
Bibkey:
Cite (ACL):
Shuo Huang, Xingliang Yuan, Gholamreza Haffari, and Lizhen Qu. 2025. Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 9175–9190, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search (Huang et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.488.pdf
Checklist:
 2025.findings-emnlp.488.checklist.pdf